Parameter	Definition
s	state of UAV
a	action of UAV
R	reward function
d	euclidean distance
ρ	switch for R3
k	discount factor
π	strategy of the agent
p	action choice probability
yi	winning score list
zi	winning agent list
V	state value function
Q	action value function
P	state transition matrix
e	revenue function of the searched area
z	time
ε	search capability of UAV
α	learning rate
bi	bundle of agent
cij[bi]	score function
Lt	maximum assigned task number